Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases expressing clarity or definiteness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     apprehen
    -1.34
     excru
    -1.33
     ?...
    -1.27
     impra
    -1.27
     reluct
    -1.25
     gaily
    -1.25
     unspeak
    -1.24
     indestru
    -1.22
     disagre
    -1.22
     !...
    -1.21
    POSITIVE LOGITS
     clear
    1.31
    clear
    1.29
    Clear
    1.18
     Clear
    1.15
     CLEAR
    1.03
    CLEAR
    1.03
     clarity
    0.96
     clears
    0.94
     clearer
    0.94
     cleared
    0.89
    Act Density 0.095%

    No Known Activations